Network Intrusion Anomaly Detection Model Based on Multiclassifier Fusion Technology

Algorithm 2

Weighted majority voting

	Input: the results set predicted by each base classifiers Y = {y1, y2, …, yn}, confusion matrix set E = {e^1, e^2, …, e^n};
	Output: final prediction result C;
(1)	a [2] ← {0, 0};
(2)	for i in {0, 1} do
(3)	for j in {1, 2, …, n} do
(4)	if yj = = i then
(5)	j ← 1;
(6)	else
(7)	j ← 0;
(8)	end if
(9)	a [i] ← a [i] + je^jii;
(10)	end for
(11)	end for
(12)	C ← argmax (a);
(13)	return C;